Dynamic　multiobjective　optimization　problems　(DMOPs)　change　over　time,　which　require　Evolutionary　algorithms　(EA)　track　Pareto-optimal　solution　(PS)　or/and　Pareto-optimal　front　(PF)　in　a　constantly　change　environment.　Prediction　-based　algorithms　are　the　most　common　method　to　solve　DMOPs.　However,　a　single　elaborate　predictor　is　not　always　suitable　for　extracting　changing　pattern　of　different　DMOPs,　and　not　to　mention　DMOPs　with　unpredictable　changes.　To　overcome　these　limitations,　a　simple　yet　effective　algorithm,　response　strategies　based　on　adaptive　selection　(RSAS),　are　proposed　in　this　paper.　When　a　change　occurs,　RSAS　provides　diversified　solutions　by　different　proposed　strategies,　that　is,　a　center　-guided　self-correcting　prediction,　an　individual　-based　prediction,　and　a　precision　-controllable　mutation.　Based　on　the　quality　of　their　generated　solution　set,　an　adaptive　selection　mechanism　can　adjust　the　selection　probability　of　these　three　strategies.　Since　RSAS　consists　of　not　merely　two　different　prediction　strategies　but　also　a　mutation　strategy,　which　can　be　more　responsive　to　predictable　and　unpredictable　changes.　To　validate　the　performance　of　RSAS,　DMOP　benchmarks　in　CEC2018　with　recommended　configurations　are　adopted.　Compared　to　four　state-of-the-art　algorithms,　the　experimental　results　show　that　RSAS　is　effective　and　efficient.